Artificial Intelligence Engineer

Darttag Consulting; Bengaluru; Hybrid; INR 3,000,000 - 6,000,000; Full time

Job summary

Darttag Consulting is seeking a senior software/ML engineer in Bengaluru to design and build production-grade AI/LLM systems. The role emphasizes strong Python, hands-on experience with agent frameworks, and deep understanding of tool use, memory models, and multi-agent orchestration.

The ideal candidate will bring 5+ years in software/ML engineering, 2+ years building LLM applications in production, and expertise in evaluation datasets, regression testing, and AI-assisted development tools.

Qualifications

• 5+ years software/ML engineering with production systems.
• 2+ years building LLM applications in production.
• Strong hands-on experience with LangGraph or similar agent frameworks (CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK).
• Deep grasp of agentic patterns: tool calling, state management, memory architectures, multi-agent orchestration, human-in-the-loop design.
• RAG experience: embeddings, vector DBs, retrieval evaluation.
• Experience evaluating LLM systems — building eval datasets, automated scoring, and regression testing for prompt and model changes.
• Fluent with AI-assisted development (Claude Code, Codex, Cursor, or similar).

Skills

Python

ML engineering

production systems

LLM applications

agent frameworks

memory architectures

vector DBs

embedding eval

prompt testing

Code tools

Tools

LangGraph

CrewAI

AutoGen

OpenAI Agents SDK

Claude Agent SDK

Job description

Role & responsibilities

What We’re Looking For

• 5+ years software/ML engineering with production systems; strong Python
• 2+ years building LLM applications in production not just prototypes
• Strong hands-on experience with LangGraph or similar agent frameworks (CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK) — has built and operated production agentic systems, not just tutorials
• Deep grasp of agentic patterns: tool calling, state management, memory architectures, multi-agent orchestration, human-in-the-loop design
• RAG experience: embeddings, vector DBs, retrieval evaluation
• Experience evaluating LLM systems — building eval datasets, automated scoring, and regression testing for prompt and model changes
• Fluent with AI-assisted development (Claude Code, Codex, Cursor, or similar) — uses these tools agentically to multiply output, not just for autocomplete

Preferred candidate profile