JOB DESCRIPTION

AI Agent Developer

Engineering & Artificial Intelligence

Department: IT & AI Innovation

Reports To: It Global Platforms LEader

Location: Remote / Hybrid

Experience Level: Mid-Senior (36+ Years)

About the Role

We are seeking a skilled and forward-thinking AI Agent Developer to join our growing AI Engineering team. In this role, you will design, build, and deploy intelligent AI agents that automate complex workflows, interact with enterprise systems, and deliver meaningful business outcomes. You will work at the cutting edge of Generative AI, leveraging large language model (LLM) APIs, multi-agent orchestration frameworks, and Retrieval-Augmented Generation (RAG) architectures to create production-grade intelligent systems.

Key Responsibilities

AI Agent Design & Development

- Architect and build autonomous AI agents capable of multi-step reasoning, tool use, and decision-making.
- Develop multi-agent pipelines using frameworks such as CrewAI, Google Gemini Enterprise Agents, LangGraph, or AutoGen.
- Define agent roles, goals, backstories, and task delegation strategies for complex workflows.
- Implement human-in-the-loop controls, escalation paths, and agent guardrails for safety and reliability.

LLM API Integration

- Invoke and integrate LLM APIs including Anthropic Claude, OpenAI GPT, Google Gemini, and other foundation model providers.
- Design prompt engineering strategies including zero-shot, few-shot, chain-of-thought, and structured output prompting.
- Implement function calling, tool use, and structured output parsing (JSON mode, XML parsing).
- Manage token budgets, context windows, and API rate limiting for scalable production deployments.

Retrieval-Augmented Generation (RAG)





- Design and implement end-to-end RAG pipelines combining document ingestion, chunking, embedding, retrieval, and generation.
- Build hybrid retrieval strategies using dense (semantic) and sparse (keyword) search methods.
- Integrate vector databases including Pinecone, Weaviate, Chroma, pgvector, or Qdrant for semantic search.
- Optimize retrieval quality through re-ranking, query expansion, and contextual compression techniques.

Vector Database & Embeddings

- Manage vector database schemas, indexing strategies, and namespace/collection design.
- Select and apply embedding models (e.g., OpenAI text-embedding-3, Cohere Embed, Google text-embedding-004) appropriate to the use case.
- Monitor embedding drift, implement data refresh pipelines, and ensure retrieval accuracy over time.

Software Engineering & MLOps

- Write clean, well-documented Python code following software engineering best practices.
- Build REST or async APIs to expose agent capabilities using FastAPI or Flask.
- Implement logging, observability, and tracing for agent pipelines using tools like LangSmith or Arize.
- Deploy AI agents to cloud environments (AWS, GCP, Azure) using containerization and CI/CD pipelines.

Required Qualifications

- 36+ years of software engineering experience, with at least 2 years focused on AI/ML systems.




- Proficiency in Python; experience with async programming, data structures, and OOP principles.
- Hands-on experience invoking LLM APIs (Anthropic, OpenAI, Google, Cohere, or equivalent).
- Practical knowledge of CrewAI, Google Gemini Enterprise Agents, LangChain, or similar agent frameworks.
- Experience building and deploying RAG pipelines in production environments.
- Working knowledge of at least one vector database (Pinecone, Chroma, Weaviate, Qdrant, pgvector).
- Familiarity with embedding models, semantic similarity, and text representation techniques.
- Experience with REST APIs, microservices architecture, and containerization (Docker, Kubernetes).
- Solid understanding of software engineering practices: version control (Git), testing, and code review.

Preferred Qualifications

- Experience with Google Gemini Enterprise Agents or Vertex AI Agent Builder.
- Familiarity with additional agentic frameworks: AutoGen, LangGraph, Semantic Kernel, or Haystack.
- Knowledge of advanced RAG patterns: HyDE, FLARE, Self-RAG, or agentic RAG.
- Experience with fine-tuning or RLHF processes for domain-specific LLM customization.
- Background in NLP, information retrieval, or data engineering.
- Experience building conversational AI or chatbot systems at scale.
- Familiarity with cloud AI services: AWS Bedrock, Google Vertex AI, or Azure OpenAI Service.
- Contributions to open-source AI/ML projects.

Technical Skills At a Glance

Python

CrewAI

Gemini Agents

LangChain

LLM APIs

RAG Pipelines

Vector Databases

Prompt Engineering

Pinecone / Chroma

Embeddings

FastAPI

Docker / K8s

OpenAI GPT

Claude API

LangGraph

Git / CI-CD

📌 Agentic AI Developer (Karnataka)
🏢 Kforce Systems
📍 Karnataka