Overview

We are seeking a highly skilled GenAI Engineer with strong hands-on experience in building AI agents, orchestrating multi-step workflows, and integrating large language models (LLMs) into production-grade systems. The ideal candidate will have at least 2+ years of experience working with GenAI technologies and frameworks such as LangGraph and LangChain, with solid understanding of multiple LLM ecosystems including Google Gemini, OpenAI, and AWS Bedrock. The candidate will be responsible for designing, building, evaluating, and optimizing GenAI systems—including autonomous agents, RAG pipelines, and custom model deployments—while ensuring that the solutions are reliable, safe, and free from unwanted bias or hallucinations.

Responsibilities

- Design, develop, and orchestrate AI agents using LangGraph and LangChain to automate complex workflows and decision-making processes.
- Build modular agent nodes, tools, memory systems, and workflow orchestration components.
- Implement multi-agent collaboration, event-driven flows, and tool-calling capabilities.
- Work with multiple LLM providers (Gemini, OpenAI, AWS Bedrock) to integrate models into AI workflows.
- Evaluate and select appropriate models based on cost, accuracy, latency, and contextual understanding.
- Fine-tune or customize pre-trained foundation models and deploy optimized variants on AWS Bedrock.
- Implement and improve Retrieval-Augmented Generation (RAG) pipelines using vector databases, embeddings, and document loaders.
- Build scalable retrieval systems that support structured and unstructured data sources.
- Work with MCP (Model Context Protocol) servers to integrate external tools and systems into agent execution.
- Develop pipelines for testing AI agents including hallucination detection, bias detection and mitigation, evaluation benchmarks, and prompt resilience and stability.




- Ensure compliance with internal AI policies, guardrails, and ethical AI guidelines.
- Deploy and monitor AI solutions on AWS (Bedrock, Lambda, ECS, S3, Step Functions).
- Maintain CI/CD pipelines for continuous validation and safe rollout of agent workflows.
- Optimize LLM inference costs through caching, batching, prompt engineering, and routing techniques.

Details

- 2+ years of experience as a GenAI Engineer, ML Engineer, LLM Developer, or similar role.
- Strong hands-on expertise with LangGraph and LangChain for building AI agents or workflows.
- Good understanding of LLMs—OpenAI, Gemini, AWS Bedrock models (Claude, Titan, etc.).
- Practical experience with RAG pipelines, embeddings, vector databases, and retrieval optimization.
- Knowledge of MCP servers and integrating external tools with AI agents.
- Experience testing GenAI systems for hallucinations, bias, factual consistency, and output stability.
- Prior exposure to tuning or customizing pre-trained LLMs and deploying them on AWS Bedrock.
- Knowledge of prompt engineering, tool calling, memory management, and agent architecture.
- Solid programming skills in Python.

Nice To Have

- Experience with LangSmith or similar LLM evaluation platforms.
- Experience in MLOps / GenAI Ops practices.
- Familiarity with vector databases (Pinecone, Weaviate, OpenSearch, Chroma).
- Hands-on experience with API development and microservice architectures.

Soft Skills

- Problem-solving mindset with robust analytical thinking.
- Excellent communication and ability to explain complex AI behavior.
- Ability to collaborate across engineering, product, and data teams.
- Curious, self-driven, and passionate about AI and automation.

Job Details

Number Of Openings

2

Experience

3–6 years (2+ years in GenAI)

Employment Type

Full-Time

Posted On

17/03/2026

Location

Indore, Thane, Surat

📌 GenAI Engineer (India)
🏢 Everestek
📍 India