AI Developer

Role: AI Developer

Location: Remote

Client: Sincera (A part Of Virtusa)

Job Type: Contract

Rate:$60/Hr to $65/Hr

Domain : Television and Video Entertainment Distribution

Role summary

AI Developer will build and operate AI-enabled applications for customer experiences, employee productivity, and operations. Use cases may include conversational support, knowledge assistance, search and discovery, summarization, classification, decision support, workflow automation, and content/metadata operations. This is a production engineering role. Success requires strong software fundamentals, disciplined evaluation, secure enterprise integration, and ownership of quality, latency, cost, observability, and supportability throughout the application lifecycle.

Must-Have Skills:

• Strong hands-on experience with LangGraph, CrewAI, or AutoGen for building agentic AI and multi-agent workflows.
• Domain experience in Television and Video Entertainment Distribution
• Experience with MCP (Model Context Protocol) and integrating AI agents with external tools, APIs, and enterprise systems.
• Strong experience with cloud-based GenAI platforms such as AWS Bedrock and/or Azure OpenAI.
• Hands-on experience with LLMs such as Claude, Gemini, and GPT.
• Experience designing and implementing RAG, prompt engineering, tool/function calling, vector databases, and LLM-based applications.
• Strong Python development skills and experience building production-grade AI/ML applications.

Key responsibilities

AI application engineering

·                  Build production applications using large language models, smaller task-specific models, retrieval-augmented generation, tool/function calling, workflow orchestration, and deterministic business logic where appropriate.

·                  Develop secure APIs, services, adapters, and event-driven integrations for digital channels, customer-care platforms, enterprise knowledge, billing and entitlement services, content/metadata systems, and internal workflows.

·                  Implement authorization-aware tool use, input validation, idempotency, timeouts, retries, fallback behavior, circuit breakers, and human escalation paths.

·                  Choose prompts, retrieval, rules, conventional machine learning, or fine-tuning based on evidence rather than defaulting every problem to a large model.

·                  Retrieval, data, and grounding

·                  Build ingestion, chunking, metadata, indexing, retrieval, reranking, citation, freshness, and deletion workflows for enterprise knowledge and approved content sources.

·                  Preserve source permissions and customer/data boundaries throughout retrieval and generation; prevent unauthorized cross-user, cross-account, or cross-domain disclosure.

·                  Partner with Data Engineering and domain owners on data quality, system-of-record alignment, lineage, and feedback loops.

Evaluation and quality engineering

·                  Create representative evaluation datasets and automated test suites for groundedness, relevance, correctness, task completion, refusal behavior, safety, robustness, latency, and cost.

·                  Run regression testing across prompt, model, retrieval, tool, and policy changes; analyze failure modes and improve the system using trace-based evidence.

·                  Instrument online quality and business metrics, support controlled experiments, and incorporate human review for higher-risk or lower-confidence outcomes.

·                  Production operations and MLOps

·                  Build CI/CD pipelines for code, configuration, prompts, evaluation assets, and model or index changes across separated development, test, and production environments.

·                  Implement structured logging, tracing, token and infrastructure cost monitoring, model/provider health checks, alerting, dashboards, and operational runbooks.

·                  Optimize throughput, latency, reliability, and cost using caching, batching, routing, prompt/context management, and appropriately sized models.

·                  Participate in production support, incident response, root-cause analysis, and continuous improvement.

·                  Security and responsible implementation

·                  Implement controls for prompt injection, jailbreak attempts, unsafe tool use, data leakage, malicious content, model abuse, and dependency/supply-chain risk.

·                  Apply DIRECTV requirements for PII and payment-card data, identity and access, secrets management, retention, content rights, audit logging, and approved model/provider use.

·                  Contribute reusable components to the AI control plane, including policy enforcement, prompt/model configuration, evaluation hooks, telemetry, and kill-switch or rollback mechanisms.

·                  Team delivery

·                  Work with Product Managers, UX, Solution Architects, AI Architects, Data Engineers, Cybersecurity, Quality Engineering, and Operations to deliver testable user outcomes.

·                  Write maintainable code, automated tests, interface contracts, technical documentation, deployment guides, and operational runbooks; participate in code and design reviews.

Required qualifications

·                  Typically, 4+ years in professional software engineering, including meaningful hands-on experience delivering AI, machine-learning, search, NLP, or data-intensive applications to production; equivalent experience is welcome.

·                  Hands-on experience with LLM APIs, prompt and context design, RAG, embedding/search systems, structured outputs, tool/function calling, and automated evaluation.

·                  Experience with SQL and document/search stores, containers, CI/CD, source control, cloud services, and observability practices.

·                  Strong software engineering habits: modular design, automated testing, secure coding, peer review, performance troubleshooting, and production ownership.

·                  Ability to explain model limitations and engineering trade-offs to technical and nontechnical partners.

·                  Bachelor's degree in computer science, engineering, data science, or a related field, or equivalent practical experience.