Full Stack Python Engineer
At Accenture Federal Services, nothing matters more than helping the US federal government make the nation stronger and safer and life better for people. Our 13,000+ people are united in a shared purpose to pursue the limitless potential of technology and ingenuity for clients across defense, national security, public safety, civilian, and military health organizations. Join Accenture Federal Services, a technology company within global Accenture. Recognized as a Glassdoor Top 100 Best Place to Work, we offer a collaborative and caring community where you feel like you belong and are empowered to grow, learn and thrive through hands-on experience, certifications, industry training and more. Join us to drive positive, lasting change that moves missions and the government forward!
Key Responsibilities:
- Set technical direction for an 8–10 person engineering team.
- Serve as primary architect and code-quality gatekeeper (review/merge all GitHub PRs).
- Define and enforce standards for architecture, performance, testing, documentation, and CI/CD.
- Own the end-to-end codebase for a distributed forecasting platform built on Python and Apache Spark (GCP).
- Champion and evolve the internal ML tooling library used for training, evaluation, metrics, and visualization.
Forecasting Platform Development
- Build and maintain scalable data pipelines and feature engineering workflows for intermittent and lumpy MRO/spare‑parts demand.
- Extend and improve metrics instrumentation (sMAPE, MASE, Dollar‑Weighted MAE, bias, diagnostics).
- Support multi-model training, evaluation, selection, calibration, and DFU lifecycle management.
- Integrate and maintain MLflow for experiment tracking, model registry, and reproducibility.
- Convert research prototypes into high-quality, production-grade components within the shared library.
Blue Yonder Integration
- Act as the technical interface between the ML Forecasting Factory and Blue Yonder workflows.
- Ensure forecast outputs, calibration parameters, and hierarchy-level signals align with Blue Yonder's format and multi-model framework.
- Collaborate with planning stakeholders to maintain compatibility with proportional allocation logic and DFU lifecycle behavior.
Team Leadership & Collaboration
- Provide mentorship, technical guidance, and architectural leadership to engineering teammates.
- Translate business needs into engineering specs in partnership with data scientists.
- Operate as a hands-on contributor with daily codebase involvement.
Here is what you need:
- US citizenship (Secret eligibility)
- BS degree
- 5+ years of professional production Python engineering experience.
- Experience building or maintaining shared internal Python libraries or ML tooling packages.
- Strong proficiency with Pandas, NumPy, and scikit-learn.
- Proven Staff/Principal-level technical leadership with architectural ownership and PR-based code stewardship.
- Experience with large-scale distributed data processing using Apache Spark.
- Hands-on experience with GCP services such as Dataproc, BigQuery, and GCS.
- Strong Git/GitHub fluency (branching, PR workflows, release management).
- Ability to mentor and lead engineers and PMs with clarity and technical credibility.
Preferred experience:
- Active DoD Secret clearance highly desired
- ML engineering background including training pipelines, evaluation frameworks, MLflow, and deployment patterns.
- Production or near-production experience with TensorFlow and/or PyTorch.
- Experience with forecasting/time-series libraries such as sktime or AutoGluon.
- Familiarity with Blue Yonder (JDA) or similar enterprise planning platforms, especially multi-model forecasting and DFU management.