Role: GenAI Engineer
Location: Los Angels, CA (Remote)
Type: Long term contract
Exp: 12+ Years
Must have skill : Media domain experience
Summary:
We are seeking a Generative AI Engineer to design, develop, and deploy production-grade GenAI applications for entertainment, content, and customer-care use cases. The ideal candidate will have strong Python and software engineering expertise, hands-on experience with LLMs and RAG architectures, and a proven ability to build scalable AI solutions in production environments.
Key Responsibilities
Application Development & Integration
Build, test, deploy, and maintain production-ready GenAI applications using Python, LangChain, LlamaIndex, and microservices architectures.
Design and implement high-accuracy Retrieval-Augmented Generation (RAG) pipelines for content metadata, sports statistics, knowledge bases, and related use cases.
Integrate LLM capabilities into client applications across Gemini OS, iOS, Android, and Smart TV platforms using RESTful APIs and WebSockets.
Develop scalable, reliable, and maintainable AI services aligned with production engineering best practices.
Model Fine-Tuning & Evaluation
Fine-tune open-source LLMs such as Llama and Mistral using LoRA/QLoRA for specialized entertainment and customer-care applications.
Build automated evaluation frameworks using tools such as Ragas and TruLens.
Measure and optimize model performance across hallucination rate, latency, relevance, response accuracy, and overall user experience.
Analyze model behavior and continuously improve quality through data, prompt, and model optimization.
Prompt Engineering & AI Orchestration
Develop, optimize, test, and version-control complex prompts and agentic workflows.
Design multi-step LLM orchestration workflows for reliable task execution and intelligent decision-making.
Implement fallback mechanisms, circuit breakers, and AI safety controls to improve system resilience.
Use frameworks such as NeMo Guardrails and Guardrails AI to establish safe and reliable user interactions.
MLOps, Operations & Collaboration
Partner with MLOps, Cloud, and Software Engineering teams to establish CI/CD pipelines for model artifacts, application deployments, and vector-index refreshes.
Monitor production systems for inference latency, token consumption, errors, availability, and overall system health.
Troubleshoot production issues and optimize AI services for scalability, performance, and cost efficiency.
Collaborate with cross-functional teams to translate business and product requirements into effective GenAI solutions.
Qualifications & Requirements
Education
Bachelor’s or Master’s degree in Computer Science, Data Science, Artificial Intelligence, Software Engineering, or a related technical discipline.
Experience
5+ years of software engineering experience, including at least 3 years of hands-on experience building and deploying Generative AI or NLP applications in production.
Experience developing scalable APIs, microservices, and cloud-based applications.
Experience working with LLM-based applications, RAG, prompt engineering, and model evaluation.
Technical Skills
Strong proficiency in Python and modern API development frameworks such as FastAPI and Flask.
Hands-on experience with LLM frameworks including LangChain and LlamaIndex.
Experience with vector databases such as Pinecone, Chroma, and Qdrant.
Experience integrating OpenAI and Amazon Bedrock APIs or equivalent LLM platforms.
Knowledge of RAG architectures, embeddings, vector search, prompt engineering, and LLM orchestration.
Experience with Git, Docker, Kubernetes, and CI/CD workflows.
Experience deploying applications on at least one major cloud platform: AWS, GCP, or Azure.
Familiarity with LLM fine-tuning techniques such as LoRA and QLoRA and evaluation frameworks such as Ragas and TruLens is highly desirable.
Experience with AI guardrails and responsible AI practices is a plus.
Preferred Skills
Experience with entertainment, streaming, media, sports, or video technology platforms.
Familiarity with mobile, Smart TV, or connected-device application ecosystems.
Understanding of production AI observability, inference optimization, and token/cost management.
Exposure to agentic AI systems and multi-agent architectures.
Core Competencies
Strong problem-solving and analytical skills.
Ability to quickly learn and adapt to rapidly evolving AI frameworks and technologies.
Strong software engineering mindset with a focus on quality, scalability, reliability, and maintainability.
Excellent collaboration and communication skills.
Passion for Generative AI, entertainment, streaming, and video technologies.
