Senior AI/ML engineer

Prodapt•Richardson, TX

81d

About The Position

Prodapt is the largest specialized player in the Connectedness industry. As an AI-first strategic technology partner, Prodapt provides consulting, business reengineering, and managed services for the largest telecom and tech enterprises building networks and digital experiences of tomorrow. A ServiceNow-invested company, Prodapt has been recognized by Gartner as a Large, Telecom-Native, Regional IT Service Provider. A “Great Place To Work® Certified™” company, Prodapt employs over 5,000 technology and domain experts across the Americas, Europe, India, Africa, & Japan. Prodapt is part of the 130-year-old business conglomerate The Jhaver Group, which employs over 32,000 people across 80+ locations globally. We are seeking a highly skilled Senior AI/ML Developer to join our Agentic AI Platform Team. In this role, you will design, develop, and deploy production-grade AI agents and intelligent automation solutions powered by Large Language Models (LLMs). You will work closely with platform architects and engineering teams to build scalable multi-agent systems that directly support field technicians and enterprise operations. The ideal candidate combines deep expertise in Generative AI, Agentic AI frameworks, Retrieval-Augmented Generation (RAG), and cloud-native software engineering with strong Python development skills and a passion for building enterprise-scale AI solutions.

Requirements

Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related technical discipline.
12+ years of software development experience with strong expertise in Python and enterprise application development.
2+ years of hands-on experience building Generative AI, Agentic AI, or LLM-based applications in production environments.
Required telecom domain experience with strong knowledge of telecommunications systems, OSS/BSS platforms, network operations, customer experience platforms, and telecom data ecosystems, including experience applying AI/ML solutions in telecom environments.
Extensive experience with Agentic AI frameworks such as LangGraph, LangChain, MCP, or equivalent enterprise agent orchestration platforms.
Strong understanding of autonomous agents, multi-agent systems, tool calling, workflow orchestration, memory management, and reasoning frameworks.
Expertise in Generative AI technologies including: LLMs, SLMs, Prompt Engineering, Fine-Tuning, Function Calling, Structured Outputs, and Model Evaluation.
Proven experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.
Strong expertise in vector embeddings, vector databases, semantic search, hybrid retrieval architectures, re-ranking / ranking optimization, and document intelligence.
Experience with Knowledge Graphs and graph-based reasoning frameworks.
Advanced Python programming skills with experience in FastAPI, AsyncIO, HTTPX, SQLAlchemy, and Alembic.
Hands-on experience with OpenAI APIs, tool-calling frameworks, streaming APIs, and real-time AI applications.
Solid background in PostgreSQL, relational databases, distributed systems, and microservices architecture.
Experience with AI/ML frameworks such as PyTorch, TensorFlow, Hugging Face Transformers, and Scikit-learn.
Hands-on experience with AWS (e.g., Bedrock, SageMaker, Lambda, ECS/EKS, S3).
Experience with multi cloud platforms — familiarity with AWS, Azure and GCP.
Strong understanding of CI/CD pipelines, Docker, Kubernetes, model deployment / version control, automated testing / validation, and observability / monitoring solutions.
Strong system design and architecture skills.
Ability to mentor developers and influence technical direction.
Experience collaborating with cross-functional teams, architects, and business stakeholders.
Strong communication, problem-solving, and Agile delivery experience.

Nice To Haves

Experience in telecommunications and large-scale enterprise platforms.
Experience building production multi-agent platforms and AI copilots.
Knowledge of model evaluation frameworks, guardrails, AI governance, and responsible AI practices.
Experience with Azure AI Foundry, Azure OpenAI, and enterprise-scale AI deployments.

Responsibilities

Design and develop autonomous, goal-oriented AI agents using frameworks such as LangGraph, LangChain, MCP, and internal frameworks (PyVegas, VEGAS, DPF).
Build and enhance multi-agent orchestration pipelines with advanced state management, conditional routing, task delegation, and fault-tolerant error recovery mechanisms.
Implement tool-calling agents that support parallel execution, sequential enrichment workflows, and intelligent summarization.
Design and develop multimodal AI capabilities, including vision-enabled image analysis and document processing.
Develop, fine-tune, and optimize Large Language Models (LLMs) and Small Language Models (SLMs) for domain-specific business use cases.
Design advanced prompt engineering frameworks, dynamic prompt management solutions, and token optimization strategies to improve performance, scalability, and cost efficiency.
Integrate with Azure OpenAI and other foundation model platforms utilizing resilient patterns such as circuit breakers, retries, fallback chains, and observability controls.
Build real-time conversational AI experiences using streaming technologies such as WebSockets and Server-Sent Events (SSE).
Design and optimize vector embedding pipelines, intelligent document chunking strategies, semantic search, and hybrid retrieval architectures.
Develop advanced RAG solutions leveraging vector databases, hybrid search (semantic and keyword-based retrieval), re-ranking techniques, and Reciprocal Rank Fusion (RRF).
Implement Knowledge Graph-based solutions to improve contextual understanding, reasoning, and AI-driven decision-making.
Develop scalable, secure, and production-ready Python applications using modern AI/ML frameworks and engineering best practices.
Build APIs, microservices, and distributed systems that support enterprise AI workloads.
Implement robust logging, monitoring, observability, error handling, testing, and performance optimization strategies.
Design and maintain CI/CD pipelines for AI model deployment, versioning, and lifecycle management across development, staging, and production environments.
Support production deployments by troubleshooting issues, monitoring model performance, and ensuring operational stability.
Partner with business stakeholders, architects, and engineering leaders to translate business requirements into scalable AI solutions.
Provide technical guidance on model selection, AI architecture, data dependencies, and implementation approaches.
Participate actively in Agile ceremonies including sprint planning, backlog refinement, stand-ups, retrospectives, and solution demos.
Contribute to architecture reviews, technical design discussions, code reviews, and engineering best practices.