Bizoforce Hiring – AI Engineer — Agentic Systems | Austin, Texas, USA

Confidential; Austin (TX); On-site; USD 150,000 - 210,000; Full time

Job summary

Confidential in Austin, Texas, USA seeks an experienced AI/ML software engineer to design and deploy LLM-powered agents and RAG pipelines for on-site product teams.

You will collaborate across disciplines to implement tool-calling workflows, multi-agent architectures, and scalable Python services using FastAPI, Docker, and cloud platforms. Strong communication and problem-solving are essential.

Qualifications

• 5–10 years of professional experience.
• 5+ years in software engineering, ML, or data engineering.
• Minimum 1 year building LLM-based or Generative AI applications.
• Strong hands-on Python, LLMs, RAG, and AI systems experience.
• Experience developing LLM-powered agents and multi-agent workflows.
• Strong SQL and Azure databases knowledge; CI/CD experience.

Responsibilities

• Design, develop, and deploy LLM-powered agents with planning and tool-calling.
• Build and optimize RAG pipelines with embeddings and vector search.
• Develop backend Python services and APIs using FastAPI or equivalent.
• Containerize applications with Docker and deploy via CI/CD pipelines.
• Collaborate with teams to integrate AI workflows into enterprise systems.

Skills

Python

LLMs

Agent orchestration

RAG

SQL

Azure

APIs

FastAPI

Docker

Testing

Communication

Education

Bachelor's or Master's in CS/Eng/AI

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

FAISS

Pinecone

Chroma

PyTorch

TensorFlow

Job description

Experience (in Years)

• Required Experience: 5–10 years.
• Relevant Experience: At least 5 years in software engineering, machine learning, or data engineering, including a minimum of 1 year building LLM-based or Generative AI applications.
• Technical Expertise: Strong hands-on experience with Python, LLMs, RAG, AI systems, and agent orchestration frameworks.
• Agentic AI Experience: Experience developing LLM-powered agents, tool-calling workflows, and multi-agent systems.
• Cloud and Database Expertise: Experience with Azure databases or cloud data platforms, SQL, Docker, and CI/CD pipelines.
• Domain Experience: Experience building AI tools and workflows for server validation is highly relevant.

Required Skills

• Programming: Strong Python scripting and software engineering skills, including production code, testing, packaging, asynchronous programming, and API development.
• Agentic AI Systems: Experience designing and developing LLM-powered agents that plan, use tools, and execute multi-step workflows.
• LLM Orchestration: Hands-on experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or equivalent frameworks.
• Retrieval-Augmented Generation (RAG): Experience building RAG pipelines involving chunking, embeddings, vector search, hybrid search, re-ranking, and context assembly.
• Large Language Models: Practical knowledge of prompt engineering, structured outputs, function calling, and context-window management.
• Token Optimization: Ability to optimize token utilization, reduce unnecessary context, and balance cost, latency, and response quality.
• Database and SQL: Strong SQL skills and experience querying enterprise databases and structured data sources.
• Azure: Experience working with Azure databases and cloud data platforms.
• Tool Integration: Ability to integrate AI agents with APIs, databases, and enterprise systems.
• Backend Development: Experience developing production Python services and APIs using FastAPI or similar frameworks.
• Containerization and Deployment: Experience with Docker, CI/CD pipelines, and deploying services on cloud platforms.
• Machine Learning: Understanding of machine learning fundamentals and familiarity with PyTorch, TensorFlow, or Hugging Face Transformers.
• Testing and Evaluation: Experience validating AI workflows, testing application behavior, and improving reliability.
• Communication: Strong written and verbal communication skills, with the ability to clarify ambiguous requirements and communicate technical decisions.

Preferred Skills / Good-to-Have Technical Experience

• Experience developing Model Context Protocol (MCP) servers or similar agent tool-integration layers.
• Production experience with multi-agent architectures involving planner, executor, reviewer, and specialist agents.
• Familiarity with human-in-the-loop checkpoints, approval gates, retries, and failure recovery.
• Experience with LLM observability and evaluation tools such as LangSmith, Langfuse, Weights & Biases, or MLflow.
• Experience with workflow orchestration tools such as Airflow, Dagster, or Prefect.
• Familiarity with DBT and analytics engineering practices.
• Experience with model fine-tuning or parameter-efficient adaptation techniques such as LoRA/PEFT.
• Knowledge of AI governance, responsible AI, and enterprise security requirements.
• Experience with semiconductor, hardware validation, manufacturing, server validation, or other technical engineering domains.
• Experience building user-facing AI interfaces using Streamlit, chat interfaces, dashboards, or embedded integrations.
• Familiarity with Snowflake, Databricks, FAISS, pgvector, Pinecone, or Chroma.

Qualifications

• Bachelor's or Master's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related field.
• At least 5 years of professional experience in software engineering, machine learning, or data engineering.
• Minimum 1 year of hands-on experience developing LLM-based or Generative AI applications.
• Demonstrated ability to build and deploy production-grade Python applications and AI services.
• Practical experience developing RAG applications and integrating LLM orchestration frameworks.
• Strong understanding of SQL, Azure databases, API development, and cloud deployment practices.
• Experience with automated testing, version control, and CI/CD processes.
• Strong analytical and problem-solving skills, with the ability to deliver reliable AI solutions for complex technical workflows.

Agent Design and Orchestration

• Design, develop, and deploy LLM-powered agents capable of planning, calling tools, and completing multi-step tasks.
• Build agent workflows using LangChain, LangGraph, or equivalent orchestration frameworks.
• Implement multi-agent architectures involving planner, executor, reviewer, and specialist roles.
• Develop state management, hand-off logic, retry mechanisms, and graceful failure-handling processes.
• Design and expose agent tools through function calling, MCP servers, and secure integrations with internal APIs, databases, and enterprise systems.

Retrieval and Knowledge Systems

• Build and operationalize RAG pipelines using document chunking, embeddings, vector search, hybrid search, re-ranking, and context assembly.
• Integrate structured, semi-structured, and unstructured data from enterprise sources such as SharePoint, Confluence, Jira, REST APIs, Excel, and SQL warehouses.
• Improve response accuracy and grounding through retrieval optimization, prompt engineering, and effective context management.
• Reduce hallucinations by improving the relevance and quality of retrieved information.
• Optimize token consumption while maintaining response quality and controlling inference costs.

Python Engineering and Backend Development

• Develop production-ready Python services and APIs for AI agents and model inference.
• Build backend services using FastAPI or equivalent frameworks.
• Apply asynchronous programming, testing, packaging, and clean coding practices.

Engineering, Deployment, and Monitoring

• Containerize AI applications using Docker and deploy them through established CI/CD pipelines.
• Support deployments on Azure, AWS, or GCP, as applicable.
• Implement structured logging, tracing, latency monitoring, token tracking, and cost accounting.
• Apply MLOps and LLMOps practices, including prompt and configuration versioning, automated regression testing, and controlled releases.
• Troubleshoot production issues and improve application reliability, scalability, and performance.

Evaluation and Quality Assurance

• Develop evaluation frameworks for agent workflows using golden datasets, task-level success metrics, and regression test suites.
• Use LLM-as-judge techniques and other evaluation methods to assess agent performance.
• Measure and optimize accuracy, latency, and operational cost.
• Validate tool-calling behavior, retrieval quality, and multi-step workflow execution.
• Ensure changes to models, prompts, and agent configurations are tested before release.

Collaboration and Continuous Improvement

• Collaborate with domain experts, data engineers, product stakeholders, and engineering teams to automate manual workflows.
• Convert ambiguous technical problems into clearly defined agent workflows and production-ready solutions.
• Deliver AI capabilities through practical interfaces such as Streamlit applications, chat interfaces, dashboards, and embedded integrations.
• Prepare technical design documents, operational runbooks, and implementation notes.
• Participate in code reviews, design reviews, and technical discussions.
• Follow enterprise security, responsible AI, and governance requirements when developing AI solutions.

Assignment Details

• Job Location: Austin, Texas, USA
• Work Mode: On-site
• Job Type: Full Time
• Open Positions: Multiple
• Working Hours: 9:00 AM – 5:00 PM
• Hours per Week: 40 hours
• Timesheet Cycle: Weekly
• Job Status: Active