Software Engineer III - AI (IND)

Legato; Bengaluru; On-site; INR 1,500,000 - 2,800,000; Full time

Job summary

Carelon Global Solutions India is seeking a Software Engineer III - AI to lead the design and delivery of cloud-native AI-enabled data platforms on AWS. The role focuses on Python services, Snowflake data warehousing, LLM integration patterns, and responsible AI practices in a healthcare-grade environment.

You will own end-to-end delivery, from discovery through production, with emphasis on scalable architecture, performance, and security under the guidance of the Assistant Manager Product

Qualifications

• Bachelor's degree in Engineering or relevant field.
• Experience shipping AI/LLM-enabled features to production.
• Strong Python and API design experience.

Responsibilities

• Lead design and delivery of cloud-native data platforms and AI-enabled solutions on AWS.
• Own technical direction across Python services, data warehousing, and production-grade ML engineering.
• Implement MLOps/LLMOps practices and ensure security and compliance.

Skills

AI engineering

Python

LLM integration

RAG

Vector search

Education

Bachelor's degree in Engineering

Tools

AWS

Docker

Kubernetes

Terraform

CloudWatch

Job description

Job Summary

Position Title: Software Engineer III - AI (IND)

Job Family: IFT > Engineering /Dev

Job Title: Software Engineer III - AI

Requirement Type: Full-Time Employee

Job Location: Gurugram/Bangalore

Job Level: Associate

Hiring Manager: Assistant Manager Product Management II

Primary Skill: AI Engineering

Business: VBC, HealthOs

Individual Contributor /People Manager: Individual Contributor

Job Purpose

• Carelon Global Solutions India is seeking a Software Engineer III - AI.
• Reporting to the Assistant Manager Product Management II, you will lead the design and delivery of cloud-native data platforms and AI-enabled solutions on AWS.
• You will own technical direction across Python services, Snowflake data warehousing, and production-grade AI/ML engineering-driving scalable architecture, engineering excellence, and end-to-end delivery for healthcare-grade systems.

Job Responsibilities

• Proven delivery ownership across the SDLC: ability to lead discovery design build test release operate for AI-powered products/services in production.
• Strong Python engineering: production-grade APIs/services (e.g., FastAPI), async/background processing, packaging, type hints, testing, and performance profiling.
• LLM application architecture: hands-on experience with LLM integration patterns (workflow orchestration, tool/function calling, structured outputs, routing, caching, guardrails, fallbacks).
• RAG + vector search expertise: embeddings, chunking strategies, metadata modeling, hybrid retrieval, reranking, index lifecycle, and retrieval tuning using evaluation feedback.
• Evaluation and quality engineering for GenAI: building eval harnesses, golden datasets, regression tests, automated scorecards, A/B testing, and human review workflows.
• Responsible AI and security controls: PII handling, data minimization, content safety, prompt-injection defenses, access controls, audit logging, and compliance-ready design.
• MLOps/LLMOps practices: CI/CD for prompts/models, environment promotion, reproducibility, experiment tracking, and monitoring for quality/cost/latency.
• Cloud and deployment experience (AWS preferred): containerization and orchestration (ECS/EKS), serverless where applicable (Lambda/Step Functions), IAM/KMS/Secrets, VPC/networking basics, and CloudWatch observability.
• Data engineering fundamentals for AI systems: reliable batch/stream pipelines, data quality checks, feature/embedding pipelines, and integration with data stores (object storage + relational/warehouse as needed).
• DevOps and operational excellence: infrastructure-as-code familiarity, release strategies, incident handling, SLO/SLI mindset, and production monitoring/alerting.
• Communication and stakeholder management: translate ambiguous problems into technical plans, manage trade-offs (accuracy vs. latency vs. cost vs. safety), and align with Product/Security/Legal.
• Mentorship and technical leadership: guide design decisions, review code/architecture, and uplift team standards.

Qualification

• Minimum education: Bachelor s degree in any Engineering Stream
• Specialized training, certifications, and/or other special requirements: Nice to have
• Preferred education: Computer Science/Engineering.

Experience

• Minimum relevant experience - 4 years in AI engineering.
• Preferred total experience - 4 years

Skills and Competencies

• Production GenAI delivery experience: proven track record shipping AI/LLM-enabled features to production (not just prototypes), including operating and improving them post-launch.
• LLM integration orchestration: hands-on with LLM application patterns-prompting, structured outputs (JSON schemas), tool/function calling, routing, multi-step workflows/agents, caching, and fallbacks.
• RAG + vector search expertise: embeddings, chunking strategies, retrieval tuning, hybrid search/reranking, metadata filtering, index lifecycle, and grounding/attribution strategies.
• Evaluation-first engineering: ability to design offline/online evaluation (golden datasets, automated scorecards, regression tests), and measure quality across accuracy, safety, latency, and cost.
• Responsible AI security: prompt-injection defenses, data/