AI Engineer

Job Description: Junior Engineer Hands-On (Agentic-AI) / AI Engineer

Role Details

• Experience: 2–4 years
• Primary Tech/Domain: Agentic AI/GenAI/DevOps/ConvAI/MLOps
• 100% Hands on

Overview & Expectations

Role Summary:

Lead and deliver high-impact initiatives aligned to the AI & Data charter. Own execution excellence with measurable business value, technical depth, and governance.

Key Outcomes (03–06 months):

• Ship production-grade solutions with clear ROI, reliability (SLOs), and security.

• Establish engineering standards, pipelines, and observability for repeatable delivery.

• Build Gen-AI applications

• Mentor talent; uplift team capability through reviews, playbooks, and hands-on guidance.

Responsibilities:

• Translate business problems into well-posed technical specifications and architectures.

• Lead design reviews, prototype quickly, and harden solutions for scale

• Build automated Gen-AI applications and model/data governance across environments.

• Define & track KPIs: accuracy/latency/cost, adoption, and compliance readiness.

• Partner with Product, Security, Compliance, and Ops to land safe-by-default systems.

Technical Skills:

• Tracks: Agentic AI/GenAI/DevOps/Conversational AI/MLOps

• Python + Cloud: FastAPI, async IO; AWS/Azure/GCP basics

• Agents & RAG: LangChain/CrewAI basics, embeddings, vector DBs

• DevOps: Docker, CI, unit/integration tests, logging

• Conversational AI: intents, NLU, dialog management, evaluation

• MLOps foundations: model packaging, simple pipelines, monitoring

• Design multi‑agent architectures using orchestration frameworks (e.g., LangChain /CrewAI /LangGraph) with clear roles, hand‑offs, and acceptance criteria.

• Build event‑driven platforms leveraging cloud messaging (EventBridge/Event Grid/Pub/Sub), durable state, retries, and idempotency for reliable agent workflows.

• Integrate LLMs as reasoning engines (Azure OpenAI / AWS Bedrock / Vertex AI) with tool/function calling, structured outputs (JSON), and guardrails.

• Develop robust tool adapters for agents (search, DB/SQL, vector stores, HTTP APIs, code execution), including error handling, circuit breakers, and fallbacks.

• Implement observability at scale: Tracing of agent steps and LLM calls, metrics (latency, cost per task), logs, and incident playbooks; dashboards for SLOs.

• Harden security & compliance: IAM/RBAC, secrets management (Key Vault/KMS/Secret Manager), PII redaction, audit trails, and policy enforcement.

• Optimize deployment & performance: Containerized microservices on AKS/EKS/GKE, autoscaling, caching/batching, concurrency controls, and cost governance.

Architecture & Tooling Stack:

• Source control & workflow: Git, branching standards, PR reviews, trunk-based delivery.

• Containers & orchestration: Docker, Kubernetes, Helm; secrets, configs, RBAC.

• Observability: logs, metrics, traces; dashboards with alerting & on-call runbooks.

• Data/Model registries: metadata, lineage, versioning; staged promotions.

Performance & Reliability:

• Define SLAs/SLOs for accuracy, tail latency, throughput, and availability.

• Capacity planning with autoscaling; load tests; cache design; graceful degradation.

• Cost controls: instance sizing, spot/reserved strategies, storage tiering.

Qualifications :

• Bachelor’s/Master’s in CS/CE/EE/Data Science or equivalent practical experience.

• Strong applied programming in Python; familiarity with modern data/ML ecosystems.

• Proven track record of shipping and operating systems in production.