Job Title: Lead / Senior AI Developer (RAG, Agents & Microservices)

Location: Canada

About client:

A global IT and consulting company based in Bangalore, India, providing IT services to clients worldwide across multiple industries.

Key Responsibilities

• RAG & Agentic Systems: Architect and build native RAG pipelines (custom chunking, hybrid search, re-ranking) and stateful multi-agent workflows with working memory and deterministic tool execution.
• Backend Microservices: Design transparent, high-performance microservices and REST APIs using FastAPI, Pydantic, and standard HTTP clients (httpx, requests).
• Context & Token Optimization: Optimize prompts, context packing, and token economics to maximize output reasoning while minimizing latency and inference costs.
• Evaluation & Security: Develop unit/regression test suites and custom evaluation harnesses. Implement guardrails for prompt-injection defense, zero-trust tool routing, and content safety.
• System Architecture & Leadership (Lead Level): Define end-to-end distributed inference architecture, optimize transformer attention/tokenization mechanics, direct GPU orchestration, and mentor junior/mid-level engineers on engineering standards.

Qualifications & Experience

• Core Engineering: Strong foundations in Python (including asyncio, concurrency, and performance tuning) and standard software engineering practices.
• GenAI Ecosystem: Hands-on experience building transparent AI applications without relying solely on heavy high-level abstractions. Knowledge of Google GECX (Gemini Enterprise for Customer Experience) is a strong plus.
• Data & Extraction: Proficiency in structured extraction patterns using Pydantic and JSON schemas.
• Observability: Experience with tracing, telemetry, latency metrics, and agent-level debugging.
• For Technical Lead Level: Proven experience leading technical teams, designing distributed/scalable AI architectures, deep knowledge of transformer/LLM internals, vector math, and custom evaluation science.

Tech Stack & Core Competencies

Domain

Key Technologies & Concepts

Languages & Frameworks

Python 3.x, FastAPI, Pydantic, HTTP Clients (httpx/requests), asyncio

GenAI Patterns

Native RAG, Hybrid Search, Multi-Agent Orchestration, Structured Outputs

Evaluation & Security

Adversarial Testing, Prompt Guardrails, Zero-Trust Tool Routing, Regression Suites

Infrastructure & Ops

Distributed Systems, GPU Orchestration, Tracing, Tokenomics Optimization

Experience: 6 + Years

Location: Canada

Salary Range: Based on Experience

About HR Ways:

HR Ways is an Award winning Technical Recruitment Firm helping software houses and IT Product companies internationally and locally to find IT Talent. HR Ways is engaged by 300+ Employers worldwide ranging from worlds biggest SaaS Companies to most competitive Startups. We have entities in Dubai, Canada, US, UK, Pakistan, India, Saudi Arabia, Portugal, Brazil and other parts of the world.