Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Digit88

NewBe an early applicant

Forward Deployed Engineer

Posted

Description

Compensation: No equity

Role : Forward Deployed Engineer Experience: 5+ Years Location: Bengaluru (Hybrid) Type: Full-time

About Digit88 Digit88 is an AI-native product engineering partner helping startups and enterprises build, scale and operate intelligent software products. We are a lean, high-impact team of 75+ technologists, backed by leaders with deep experience across startups and global enterprises. We build strong, outcome-driven engineering teams that solve complex, real-world problems. From GenAI applications and data platforms to enterprise-grade SaaS, we deliver scalable, reliable, production-ready systems. Our expertise spans AI/ML, RAG systems, agentic workflows and large-scale data engineering - enabling businesses to move from idea to production with speed and confidence. Our teams operate as a true extension of our clients, with full ownership and flexible engagement models focused on measurable business outcomes - not just delivery. With 80+ AI implementations and proven success in scaling dedicated teams and driving significant cost efficiencies, we partner for long-term impact. We bring experience across B2B and B2C SaaS, web and mobile platforms, e-commerce and domains such as Conversational AI, HealthTech, IoT, ESG/Energy, and Data Engineering - thriving in fast-paced, high-ownership environments. The Vision: To be the most trusted AI-native product engineering partner for innovative software companies worldwide, delivering ownership, speed, and measurable outcomes. Job Profile: Digit88 is seeking a hands-on Forward Deployed Engineer (FDE) who works directly with customers to discover problems, design solutions, write production-quality code, build integrations, debug issues and drive deployment of Conversational AI and customer experience applications. The FDE owns outcomes from discovery through production and must be able to code, troubleshoot and explain technical trade- offs to customer and engineering stakeholders. Java backend engineering and Python-based AI engineering are mandatory. Conversational AI experience is a must. Consumer-facing CCaaS experience across messaging, Digital AI and/or Voice AI is a major advantage because this role requires credible customer-facing subject-matter expertise.

Responsibilities:

● Work directly with customer product, engineering, operations and customer experience teams to understand workflows, pain points, success metrics and technical constraints. ● Translate customer requirements into working solutions, APIs, data models, integration contracts, implementation plans and acceptance criteria. ● Build and maintain backend services and integrations using Java and Spring Boot for customer- facing and platform workflows. ● Build AI/LLM capabilities in Python, including agent workflows, tool/API calling, automation and MLOps support. ● Build real-time conversational experiences across voice, messaging and chat: speech-to-text, LLM and text-to-speech pipelines, turn detection, interruption handling, streaming, context across channels, human handoff and graceful failure handling. ● Integrate Conversational AI with contact-center/CCaaS systems, CRM, ticketing, identity, knowledge bases and enterprise APIs. ● Secure every integration point: verify webhook signatures and tokens, manage secrets, apply least privilege and tenant isolation, redact PII, control recording and retention, and protect against prompt injection. ● Build for production: authentication, authorization, retries, idempotency, rate limits, timeouts, error handling, logging, monitoring, deployment and incident response. ● Design for concurrent customer sessions and latency-sensitive interactions: measure latency end to end (time to first token, time to first audio), concurrency and provider rate limits, and apply asynchronous processing, resource limits and backpressure. Track cost per conversation. ● Design and run retrieval (RAG): chunking, embeddings, indexing, matching logic, retrieval quality checks, and knowledge base updates with versioning. ● Evaluate AI quality before and after go-live: test sets, guardrails, structured capture of key moments and outcomes (variables, dispositions, CSAT), and analytics that customers can act on. ● Select and integrate voice, LLM and orchestration providers (for example ElevenLabs, OpenAI and Strands) on latency, quality, language coverage and cost. Tune LLM usage with model routing, prompt caching and token limits, and choose proven frameworks over bespoke code where that is faster and more reliable. ● Design secure, observable cloud solutions on AWS, using DynamoDB and PostgreSQL based on data needs. Collaborate on React-based frontend workflows as required. ● Prototype quickly, validate with customers, iterate on real usage and turn successful prototypes into maintainable production systems. ● Own technical troubleshooting and customer escalations; coordinate with Product and Engineering on platform gaps and reusable capabilities. ● Document architecture decisions and reusable implementation patterns without sacrificing customer-specific needs or platform integrity.

What success looks like: ● Customer requirements become working, production-ready solutions with measurable outcomes. ● Integrations and AI workflows are reliable, secure, observable and maintainable, with no unauthenticated entry points and customer data protected. ● Customer issues are diagnosed and resolved quickly with clear communication and effective escalation. ● Solutions meet agreed measures such as resolution/containment, end-to-end latency, concurrency, reliability, adoption, satisfaction and cost per conversation, and the FDE can show how each was measured.

● AI quality is evaluated before go-live and tracked after, and customers can see how their conversations perform. ● Reusable patterns reduce implementation time without compromising customer requirements or platform integrity.

Requirements: ● Strong hands-on software engineering experience, ideally 5+ years, delivering customer-facing enterprise software into production. ● Mandatory Java competency for backend engineering, preferably Spring Boot, REST APIs, dependency injection, testing, exception handling and service design. ● Mandatory Python competency for AI engineering, automation, LLM integrations, tool calling and MLOps workflows. ● Hands-on Conversational AI experience in production on voice and/or messaging channels, including conversation state, context handling, fallback, escalation and production measurement of latency, concurrency, containment and cost per conversation. Working knowledge of real-time voice pipelines (speech-to-text, LLM, text-to-speech), turn detection and interruption handling. ● Experience building APIs and enterprise integrations; hands-on with authentication, webhook signature verification, secrets management, retries, idempotency, rate limits and event-driven patterns. ● Practical security and data privacy for customer data: tenant isolation, least privilege, PII redaction, recording and retention controls, and protection against prompt injection. ● Hands-on retrieval (RAG): embeddings, indexing and matching logic, with the ability to explain how retrieval works internally and how knowledge is kept current. ● AI evaluation and guardrails in production: quality measurement, structured outputs and human handoff. ● Strong debugging and production-readiness skills across testing, observability, performance and reliability. ● Ability to lead technical discovery, handle ambiguity, explain trade-offs (including build versus buy), and take ownership from problem definition through deployment, and to say clearly which parts they built themselves. ● Working knowledge of cloud architecture and deployment practices; AWS experience is preferred.

Good to have: ● Consumer-facing CCaaS/contact-center experience across Messaging, Digital AI, IVR, Voice AI, routing and/or agent assist. ● Production Voice AI at scale: telephony (SIP, WebSocket, WebRTC), call recording and transfer, noise handling, low-latency streaming and high-volume concurrency. ● Experience integrating ElevenLabs, OpenAI and/or Strands, or equivalent Voice AI, LLM and agent-orchestration technologies, including voice frameworks such as LiveKit or Pipecat. ● Experience in regulated or security-sensitive environments such as financial services or healthcare. ● Prompt/version management, model monitoring and LLM cost tuning (model routing, prompt caching). ● AWS production experience with DynamoDB and PostgreSQL.

● React or another modern frontend framework, sufficient to debug integrations and collaborate full- stack.

Benefits working @ Digit88: ● Comprehensive Insurance (Life, Health, Accident). ● Flexible Work Model. ● Accelerated learning & non-linear growth. ● Flat organization structure driven by ownership and accountability. ● Opportunity to own and be a part of some of the most innovative and promising AI/SaaS product companies in North America and around the world. ● Accomplished Global Peers - Working with some of the best engineers/professionals globally from the likes of Apple, Amazon, IBM Research, Adobe and other innovative product companies. ● Ability to make a global impact with your work, leading innovations in Conversational AI, Energy/Utilities, ESG, HealthTech, IoT, Risk/Compliance, CyberSecurity, PLM and more. You will work with a founding team of serial entrepreneurs with multiple successful exits to their credit. The learning will be immense just as will the challenges.

This is the right time to join us and partner in our growth

Skills

Apply

See also

Solutions Engineering jobs by country — openings, pay and top skills →