AI / ML Engineer

Actively Reviewing the Applications

CodeVyasa

Gurugram Full-Time 4–8 years

Posted 3 days ago • Apply by June 11, 2026

Job Description

The ideal candidate should have hands-on expertise in building scalable backend systems using. NET technologies and experience working with modern cloud environments such as Azure or GCP.

Responsibilities

Build LLM-powered features (assistants/chat, copilots, automated workflows) and integrate them into products via APIs/services.
Design and implement Retrieval-Augmented Generation (RAG) pipelines: document ingestion, chunking, embeddings, indexing, retrieval, re-ranking, and grounding/citation patterns.
Apply prompt engineering and prompt management: templates, guardrails, structured outputs (e. g., JSON), and iterative improvement.
Create evaluation and quality frameworks: test sets, rubrics, automated checks, regression testing, and monitoring of AI output quality.
Apply ML fundamentals to improve AI system performance: select appropriate metrics (accuracy/precision/recall/F1 where relevant), analyse failure modes, and run experiments.
Implement production-ready engineering practices: logging, tracing, error handling, performance tuning, cost optimisation, and secure data handling.
Collaborate with data engineering/analytics on data extraction, transformations, validation checks, and pipeline reliability.
Document system design, experiments, and operational runbooks; contribute to best practices and reusable components.
Responsible for designing and developing resiliency in the infrastructure, troubleshooting incidents, engaging with squads to address failure patterns, and participating in incident management.
Interest in working on. NET projects when required.

Requirements

3+ years of experience in AI Engineering / ML Engineering / Software Engineering with applied AI delivery.
Strong Python proficiency (clean, testable, maintainable code; debugging; performance awareness).
Hands-on experience with LLMs / GenAI: prompts, embeddings, orchestration frameworks, and building real features (not just demos).
Experience building and tuning RAG systems (retrieval quality, chunking strategies, hybrid search, reranking/grounding).
ML exposure (core concepts): supervised learning basics, train/validation/test, evaluation metrics, bias/variance intuition, and error analysis.
Working knowledge of data engineering/analysis: SQL fundamentals, data profiling, ETL/ELT concepts, and data quality checks.
Familiarity with deploying services in production (REST APIs, containers, CI/CD basics, and monitoring/observability).

This job was posted by Vriddhi Seth from CodeVyasa.