AI ML Engineer

Futran Tech Solutions; Pune District; Hybrid; INR 1,200,000 - 2,400,000; Full time

Job summary

Futran Tech Solutions in Pune is seeking a Lead AI Engineer to shape the design, architecture, and quality of AI agents on our platform. You will set engineering standards for prompt design, agent evaluation, and LLM integration, guiding a high-impact team toward scalable, production-ready AI agents.

Lead the RAG pipeline architecture, establish evaluation frameworks, and mentor senior engineers. You will optimize latency, cost, and accuracy while driving best practices in model context and

Qualifications

• 10+ years in AI/ML engineering and strong production LLM experience.
• Deep expertise in prompt engineering and agent design.
• Proficiency in Python; familiarity with TypeScript/Node.js.

Responsibilities

• Architect the agent engineering framework including orchestration patterns and tool-calling standards.
• Lead design reviews of agent implementations across the team.
• Own RAG pipeline architecture: embeddings, retrieval optimization, accuracy benchmarks.
• Define agent evaluation framework with golden datasets and regression testing.
• Set prompt engineering standards and chair the prompt review board.
• Mentor JL1 engineers on agent development and evaluation.
• Monitor production performance: latency, cost, and accuracy.

Skills

AI/ML engineering

production LLMs

prompt engineering

agent design

LLM integration

Python

TypeScript/Node.js

team leadership

Tools

N/A

Job description

Lead the agentic AI engineering function responsible for the design, architecture, and quality of all AI agents on the platform. Define engineering standards for prompt design, agent evaluation, and LLM integration across the team.

WHAT YOU'LL DO

• Architect the agent engineering framework: orchestration patterns, prompt governance, and tool-calling standards
• Lead design review of all agent implementations across the team
• Own the RAG pipeline architecture: embedding strategy, retrieval optimization, and accuracy benchmarks
• Define the agent evaluation framework: golden datasets, confidence calibration, regression testing
• Set prompt engineering standards and chair the prompt review board
• Mentor JL1 engineers on agent development and evaluation
• Monitor and optimize agent performance in production: latency, cost, and accuracy

REQUIRED SKILLS & EXPERIENCE

10+ years in AI/ML engineering; 5+ years with production LLM systems Deep expertise in prompt engineering, agent design, and LLM integration

Experience architecting RAG pipelines at scale Agent evaluation: hallucination testing, confidence scoring, regression frameworks

Python expert; TypeScript/Node.js familiarity a

plus Experience leading AI/ML engineering teams

Understanding of LLM cost management, token

budgeting, and latency optimization

NICE TO HAVE

• Experience with Model Context Protocol (MCP) or tool-calling standards
• Background in enterprise AI platform builds
• Knowledge of ITSM or IT operations domains