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

APEXON INDIA PRIVATE LIMITED

NewBe an early applicant

GenAI Full Stack Engineer - Agentic AI & RAG

Posted Updated

Description

About Apexon:

Apexon is an AI-first technology services firm that engineers Intelligent Enterprises. Our interconnected disciplines of Domain & Strategy, Cognitive Architecture, and Harness Engineering guide every engagement, helping clients deliver meaningful business outcomes while applying collective intelligence to confidently scale from early AI strategies to enterprise-grade production systems. For over three decades, we have helped organizations by leveraging our deep and practical expertise in Artificial Intelligence, Data & Analytics, Digital Engineering, and Experience, combined with our industry knowledge across Banking & Financial Services, Healthcare and Life Sciences to create lasting business value. Apexon is backed by Goldman Sachs Asset Management and Everstone Capital.

We enable #HumanFirstDigital

Role Summary:

Total Experience: 1 - 4 years

Location: Ahmedabad, India

Team: Apexon Labs

Join Apexon Labs to build production-grade GenAI applications, client prototypes, and reusable AI accelerators. You will lead full-stack engineering across Python, modern web frameworks, RAG, and agentic AI while establishing standards for evaluation, guardrails, observability, and production readiness. This is an application engineering role focused on building solutions using foundation models. Training or fine-tuning foundation models and classical machine learning are not part of the role.

Key Responsibilities:

- Lead the architecture and development of GenAI prototypes and proofs of concept, with a clear path to production.

- Shape Apexon's GenAI platforms and accelerators, converting repeatable client patterns into reusable IP.

- Select appropriate architectures, including deterministic workflows, single-agent systems, and multi-agent systems.

- Build enterprise RAG and agentic applications that integrate securely with business data and tools.

- Establish standards for LLM evaluation, tracing, guardrails, observability, reliability, and cost efficiency.

- Track emerging AI technologies, conduct structured experiments, and recommend tools and patterns for adoption.

- Partner with client and delivery teams to deploy prototypes and accelerators successfully.

- Mentor engineers through technical design, code reviews, pairing, and knowledge-sharing sessions.

Mandatory Skills:

- 1 - 4 years of full-stack engineering experience, primarily using Python.

- Production experience with FastAPI or an equivalent Python framework.

- Strong knowledge of data structures and web application development.

- Hands-on experience with React, Angular, or an equivalent front-end framework.

- At least 1 years of experience building enterprise-scale, production-grade LLM applications.

- Deep RAG experience using Qdrant or pgvector, including hybrid search, re-ranking, metadata filtering, and complex-document parsing.

- Experience shipping tool-using or multi-agent systems using LangGraph and LangChain, or equivalent frameworks.

- Experience building or integrating Model Context Protocol servers.

- Hands-on experience with Azure AI Foundry or AWS Bedrock.

- Experience implementing LLM evaluation, tracing, and production observability.

- Experience with GitHub, GitLab, or Bitbucket.

- Hands-on use of an AI coding assistant such as GitHub Copilot, Claude Code, Kiro, or Cursor.

- Familiarity with spec-driven development using GitHub Spec Kit, Kiro, or similar tools.

- Strong hands-on engineering, client collaboration, and technical mentoring capabilities.

Nice to Have Skills:

- Agent-memory design using Mem0.

- Running open models locally with Ollama.

- Claude Agent SDK, OpenAI Agents SDK, or other agent frameworks.

- Voice or multimodal agent development.

- Token-cost and latency optimization through caching, streaming, or model routing.

- Docker, CI/CD, and deployment on AWS, Azure, or GCP.

- Experience in healthcare, financial services, or another regulated industry.

- Technical knowledge sharing through talks, blogs, demonstrations, or internal sessions.

Skills

Apply

See also

Full-Stack jobs by country — openings, pay and top skills →