Ignite IT Hub is seeking a senior AI/ML Engineer to maintain and enhance the U.S. Census Bureau's LLM Autocoder, which assigns standardized codes to survey write-in responses. You will build and test model and software improvements for the American Community Survey (ACS), develop pilots for additional surveys and fields, and work with data scientists and MLOps engineers to integrate approved changes into production.
Responsibilities
• Develop and maintain Python components for text preprocessing, model invocation, prompt management, structured output validation, and coding workflows.
• Implement approved changes to prompts, model configuration, dictionaries, rules, and supporting code in small, version-controlled increments.
• Build pilots using LLMs, fuzzy matching, direct-match dictionaries, or hybrid approaches; adapt implementations to survey-specific taxonomies and requirements.
• Write unit, integration, regression, negative, and edge-case tests, and work with the evaluation team to compare candidate results with approved baselines.
• Reproduce production problems, isolate causes across code, data, prompts, and model behavior, and implement verified corrections.
• Partner with the MLOps Engineer on packaging, deployment, rollback, and post-release verification within Government-approved AWS environments.
• Participate in code reviews and SME working sessions; maintain technical documentation, user guidance, and reproducible examples for Government handoff.
Requirements
Required qualifications
• Bachelor's degree in computer science, engineering, data science, or a related field, or equivalent relevant professional experience.
• 8+ years in software or ML engineering, including 3+ years building NLP or ML applications and hands-on experience integrating LLMs into working systems.
• Strong Python development skills and experience with data processing, APIs, automated testing, Git, and maintainable software design.
• Experience with text classification, prompt design, structured model outputs, and measuring the effects of implementation changes on model performance.
• Experience deploying or supporting applications in AWS, troubleshooting production issues, and collaborating effectively with data scientists and operational teams.
Preferred qualifications
• Experience with fuzzy matching, dictionary-based coding, survey text, or industry and occupation classification.
• Experience with ML frameworks such as scikit-learn, PyTorch, or Hugging Face, and handling sensitive data in controlled federal environments.
Conditions of employment. Position contingent on contract award. Must be able to obtain and maintain applicable Census Special Sworn Status and Personal Identity Verification (PIV) credentials, follow confidentiality requirements, and support Census core business hours and coordinated critical processing runs.
Benefits
Benefits
- 401(k)
- 401(k) matching
- Dental insurance
- Flexible spending account
- Health insurance
- Life insurance
- Paid time off
- Professional development assistance
- Referral program
- Tuition reimbursement
- Vision insurance
Skills Required
- Bachelor’s degree in computer science, engineering, data science, or a related field, or equivalent relevant professional experience.
- 8+ years of software or ML engineering experience.
- 3+ years building NLP or ML applications.
- Hands-on experience integrating LLMs into working systems.
- Strong Python development skills.
- Experience with data processing, APIs, automated testing, Git, and maintainable software design.
- Experience with text classification, prompt design, structured model outputs, and measuring implementation effects on model performance.
- Experience deploying or supporting applications in AWS.
- Experience troubleshooting production issues and collaborating with data scientists and operational teams.
- Experience with fuzzy matching, dictionary-based coding, survey text, or industry and occupation classification.
- Experience with scikit-learn, PyTorch, or Hugging Face.
- Experience handling sensitive data in controlled federal environments.
- Ability to obtain and maintain applicable Census Special Sworn Status and Personal Identity Verification credentials.
- Ability to follow confidentiality requirements and support Census core business hours and coordinated critical processing runs.
What We Do
Passion and Purpose. We are a start-up borne out of a group of architects and engineers providing solutions that transform with digital breakthroughs. We Partner - Partnership to us means being all in - on the ground, in the weeds, producing and delivering mission solutions. We Innovate - driving digital innovation and experimentation to improve decision services for the American people. We Engage – co-creating to deliver HCD (human centered design) to solve tour customers digital challenges. We Deliver – and take pride and accountability in everything we do. We are Ignite IT. Ignite IT deploys teams that are customer-obsessed, delivering a CX (Customer Experience) renaissance to our Private and Public Sector customers. We combine Commercial BX (Business of Experience) with customer delivery experts to benefit agencies to innovate and improve services and launch new digital solutions. We have built a company foundation dependent on each of our employee’s success, and provide a healthy, engaging, community where learning and knowledge sharing are encouraged. We empower our employees to be bold, continually innovate and propose new ideas to improve processes and services. We engage daily on work that touches millions of people, always focusing on positive impacts and results. We enable mission services that enable Enterprise companies to succeed in digital transformation, protect Border Agents, deploy the Army Reserve and National Guard, providing decision dominance to make America safer. We apply these digital services across the Private and Public Sectors to include include HHS, DHS, AOUSC and Army. We aim to continually raise the bar for our customers to expect more from their digital services. For more information, visit www.igniteitservices.com
