AI/ML Engineer

Recrew AI; Bengaluru Urban; On-site; INR 1,200,000 - 1,800,000; Full time

Benefits offered by this job

Ownership of agentic AI systems

Access to latest LLM models and AI工具

Global delivery network collaboration

Onsite role in Bangalore

Job summary

Recrew AI in Bengaluru is seeking an experienced AI/ML Engineer to own the design and delivery of agentic AI systems and LLM-powered applications at scale. You will architect multi-agent pipelines, RAG systems, and LLM integrations from prototype to production, collaborating with data engineers, product managers, and domain experts worldwide.

The ideal candidate has 4+ years in software development with hands-on LLM production experience, proficiency in LangChain and LangGraph, and a strong

Qualifications

• 4+ years of software development experience with 1–2 years in production-ready AI/ML systems
• Hands-on experience with LangChain and LangGraph for LLM app development, including RAG
• Proficiency with at least one agentic AI framework: AutoGen, CrewAI, or Azure ADK
• 3+ years of professional Java development with Spring Boot and REST API design
• Experience integrating LLMs from providers (OpenAI GPT-4, Claude, Llama)
• Hands-on experience with vector databases (Pinecone, Weaviate, Milvus, Chroma, FAISS) for semantic search

Responsibilities

• Design and implement end-to-end RAG pipelines and production LLM apps
• Build and orchestrate multi-agent systems using LangChain, LangGraph, AutoGen, CrewAI, or Azure ADK
• Develop and maintain backend services in Java/Spring Boot exposing LLM capabilities via REST APIs
• Integrate LLMs from multiple providers with robust prompts and function-calling patterns
• Design semantic storage layers and knowledge graphs for retrieval and reasoning
• Build evaluation and observability tooling to monitor performance, latency, and cost
• Maintain code quality and contribute to internal knowledge sharing on agentic AI patterns

Skills

LangChain

LangGraph

AutoGen

CrewAI

Azure ADK

Java

Spring Boot

REST APIs

Microservices

Python

OpenAI GPT-4

Claude

Llama

Vector DBs

Pinecone

Weaviate

Tools

Spring Framework

Docker

Kubernetes

CI/CD

Job description

Role: AI/ML Engineer - Agentic AI & LLM Systems

Function: Artificial Intelligence / Machine Learning Engineering

Type: Full-time

Industry: Information Technology & Services, Management Consulting

About Company

The company is a digital engineering firm founded in 2020 and headquartered in Tampa, Florida. It specializes in AI-driven digital transformation for enterprises.

Over 450 professionals work across seven global offices, including Bangalore, Trivandrum, Toronto, Dallas, Belgrade, Johannesburg, and Bogota. The company has completed 55+ enterprise projects across 25+ countries.

In 2023, it expanded its product engineering capabilities by acquiring a product engineering firm. It operates with a fast-paced, ownership-driven culture built on agility, client-centricity, and ethical execution.

Position Overview

This role sits at the intersection of applied AI research and production engineering. You will own the design and delivery of agentic AI systems and LLM-powered applications that solve real enterprise problems at scale. Responsibilities include architecting multi-agent pipelines, RAG systems, and LLM integrations - taking them from prototype to production. You will collaborate with data engineers, product managers, and domain experts across the company's global delivery network. The ideal candidate brings both depth in agent orchestration and the engineering rigor to ship reliable, observable AI systems.

Role & Responsibilities

• Design and implement end-to-end RAG pipelines - including chunking strategies, vector store selection, retrieval optimization, and context injection - for production LLM applications
• Build and orchestrate multi-agent systems using LangChain, LangGraph, AutoGen, CrewAI, or Azure ADK, including agent reasoning loops, tool use, and inter-agent collaboration patterns
• Develop and maintain backend services in Java/Spring Boot to expose LLM capabilities as REST APIs and integrate with enterprise microservices
• Integrate LLMs from multiple providers (OpenAI, Anthropic, Meta/Llama) with robust prompt libraries, function-calling patterns, and fallback strategies for production reliability
• Design semantic storage layers using vector databases (Pinecone, Weaviate, Milvus, Chroma, or FAISS) and knowledge graphs for retrieval and reasoning
• Build evaluation frameworks and observability tooling to monitor agent performance, hallucination rates, latency, and cost across deployed systems
• Maintain code quality and technical documentation, and contribute to internal knowledge sharing on emerging agentic AI patterns and LLM best practices

Must Have Criteria

• 4+ years of software development experience, with at least 1–2 years of hands-on experience building and deploying LLM-based or AI/ML systems in production
• Hands-on experience with LangChain and LangGraph for LLM application development, including RAG architecture design and implementation
• Proficiency with at least one agentic AI framework: AutoGen, CrewAI, or Azure ADK (Agent Development Kit)
• 3+ years of professional Java development with Spring Boot and Spring Framework, including REST API design and microservices architecture
• Practical experience integrating LLMs from providers such as OpenAI (GPT-4), Anthropic (Claude), or Meta (Llama), including prompt engineering and function-calling patterns
• Hands-on experience with vector databases - Pinecone, Weaviate, Milvus, Chroma, or FAISS - for semantic search and RAG pipelines
• Proficiency with Python for AI/ML scripting and development alongside Java-based backend work

Nice to Have

• Experience with containerization (Docker) and orchestration (Kubernetes) for deploying AI workloads
• Familiarity with cloud platforms - AWS, Azure, or GCP - and serverless architectures for LLM serving
• Knowledge of LLM fine-tuning, transfer learning, or model optimization techniques
• Experience with CI/CD pipelines, monitoring, logging, or observability tools in an MLOps or LLMOps context
• Background in information retrieval, NLP, or classical machine learning; or contribution to open-source AI/ML projects

What We Offer

• Direct ownership of agentic AI systems deployed across enterprise clients in 25+ countries
• Access to the latest LLM models, AI tooling, and infrastructure - with budget to experiment and ship
• Collaborative team of experienced AI/ML and platform engineers across the company's global delivery centers
• Onsite role in Bangalore with a high-growth, globally active engineering firm and a clear career growth trajectory