Lead AI Developer

About the Role

We are looking for a skilled AI Developer to design, develop, integrate, and deploy intelligent, production-ready AI applications.

The ideal candidate must have strong hands-on experience in Python, FastAPI, Large Language Models (LLMs), Generative AI, Retrieval-Augmented Generation (RAG), AI agents, vector databases, and Machine Learning models and evaluating their performance.

The candidate will build AI-powered applications, conversational assistants, intelligent automation workflows, and Python-based AI backend services. The role also involves integrating AI capabilities with existing application backends through REST APIs and developing reliable, scalable AI solutions for real-world business requirements.

We are looking for someone with practical implementation experience who can turn AI concepts into working applications, evaluate their performance, and deploy them into production.

Key Responsibilities

• Design, develop, and maintain production-ready AI applications using Python.
• Build and optimize RAG pipelines for knowledge retrieval and context-aware responses.
• Integrate LLMs from providers such as OpenAI, Google Gemini, Anthropic Claude, or equivalent platforms.
• Develop AI agents with tool calling, function execution, and multi-step workflow orchestration.
• Build AI chatbots, conversational assistants, and natural-language interfaces.
• Design and implement AI-powered workflow automation and intelligent business processes.
• Develop AI backend services and REST API endpoints using FastAPI.
• Integrate AI services with existing backend applications, REST APIs, databases, and third-party services.
• Build AI agents that retrieve application data and execute authorized operations through existing APIs.
• Develop document ingestion, preprocessing, chunking, embedding, indexing, retrieval, and reranking pipelines.
• Implement vector databases and semantic search for efficient knowledge retrieval.
• Apply Machine Learning techniques to suitable prediction, classification, recommendation, and other data-driven use cases.
• Evaluate AI and ML models using appropriate performance metrics and test datasets.
• Work with pretrained models and evaluate opportunities for fine-tuning when required.
• Implement prompt engineering, structured outputs, context management, and response validation.
• Develop multilingual AI capabilities and conversational workflows.
• Implement AI evaluation, testing, guardrails, logging, monitoring, and hallucination-reduction techniques.
• Optimize AI application quality, response latency, reliability, scalability, and model usage costs.
• Deploy, troubleshoot, and maintain AI applications in production environments.
• Follow secure development practices for API integrations, authentication, authorization, and data protection.
• Collaborate with frontend, backend, mobile, QA, and DevOps engineers to integrate AI capabilities into applications.

Mandatory Technical Skills

1. Python and Backend Development

• Strong hands-on experience in Python programming.
• Experience building production-grade backend services using FastAPI.
• Experience developing and consuming REST APIs.
• Understanding of asynchronous programming, request validation, response schemas, exception handling, and testing.
• Ability to integrate AI services with existing backend systems and third-party platforms.

2. LLMs and Generative AI

• Practical experience developing LLM-powered applications.
• Experience integrating LLM providers such as OpenAI, Gemini, Claude, or equivalent platforms.
• Understanding of prompt engineering, context windows, structured outputs, and function/tool calling.
• Ability to build reliable AI applications beyond basic chatbot demonstrations.

3. RAG Pipelines and Knowledge Retrieval

• Hands-on experience designing and implementing RAG architectures.
• Understanding of embeddings, document chunking, semantic search, metadata filtering, and retrieval optimization.
• Experience with vector search and context retrieval.
• Ability to evaluate and improve retrieval relevance and answer accuracy.

4. AI Agents and Workflow Automation

• Experience building AI agents and agentic workflows.
• Understanding of tool calling, API execution, state management, and workflow orchestration.
• Experience with frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent tools.
• Ability to automate multi-step tasks using AI models, APIs, and external tools.

5. Machine Learning Fundamentals

• Understanding of supervised and unsupervised learning.
• Knowledge of common ML algorithms and their appropriate use cases.
• Understanding of data preprocessing, feature engineering, training and validation datasets, and model evaluation.
• Familiarity with metrics such as precision, recall, F1-score, and accuracy, where appropriate.
• Ability to identify when a problem requires traditional Machine Learning versus an LLM-based solution.

6. Vector Databases and Data Integration

• Experience with at least one vector database, such as Qdrant, Pinecone, Weaviate, Milvus, or pgvector.
• Understanding of similarity search, vector indexing, and metadata filtering.
• Experience integrating AI applications with relational databases, NoSQL databases, and external services.

7. Production Deployment and Engineering

• Experience deploying and maintaining AI applications in production.
• Knowledge of Docker, Git, testing, CI/CD, logging, and monitoring.
• Understanding of application security, scalability, reliability, and performance optimization.
• Ability to troubleshoot production issues and maintain reliable AI services.

Preferred Qualifications

• Hands-on experience fine-tuning pretrained LLMs or other ML models for specific use cases.
• Familiarity with PyTorch, TensorFlow, or scikit-learn, as appropriate to the solution.
• Experience with model evaluation, experiment tracking, and dataset preparation.
• Knowledge of deep learning fundamentals and neural network architectures.
• Experience deploying AI applications on Microsoft Azure, AWS, Google Cloud, or another suitable cloud platform.
• Familiarity with managed AI services, including Azure OpenAI, where applicable.
• Experience with speech recognition, text-to-speech, or voice-based AI applications.
• Knowledge of event-driven architecture and distributed systems.
• Familiarity with Go (Golang) is an added advantage.

What Were Looking For

• Strong practical implementation and problem-solving skills.
• Ability to independently develop, test, integrate, and deploy AI solutions.
• A solid understanding of Machine Learning and hands-on experience with modern Generative AI technologies.
• Ability to connect AI capabilities to real application data, backend APIs, and business workflows.
• Strong debugging skills and a focus on clean, maintainable, secure code.
• Ability to work collaboratively with software engineering teams.
• A willingness to learn, experiment, evaluate results, and improve AI systems continuously.

Interested candidates can send their resumes to careers@obbian.com