Agentic Delivery Systems Engineer

About the Role

AspenView is hiring an Agentic Delivery Systems Engineer to own how well agentic software delivery actually works on a large AI-led modernization programme for a global payments and financial-technology platform. The client is deploying AI-assisted development across 8,000+ engineers, running an agentic AI operating system for banking built on OpenAI with Amazon Bedrock and AWS AgentCore, and operating autonomous coding agents against core-platform modernization in parallel. Its restaurant, lodging and hospitality commerce business is a named growth vertical.

AspenView delivery teams build software with agents in the loop, and this role owns the part that decides whether that works: the context that reaches the model, the token and cost envelope it runs in, the tools and permissions each agent is given, and the evidence that any of it is making teams faster without making the code worse. This is a delivery system, not a chatbot — you will instrument first, form a hypothesis, and let the data overrule intuition.

What You Will Do

Context Engineering & Token Economics
- Design what enters the context window and what does not: retrieval strategy, file and repository scoping, structured summaries, and pruning rules that keep long sessions coherent across a large, heterogeneous estate.
- Diagnose and fix context degradation — window saturation, stale or contradictory context, lost-in-the-middle recall loss, and compaction that silently drops critical state.
- Optimise prompt caching, session compaction, and reuse to cut redundant token spend without reducing task success rates.
- Build and maintain cost models for agentic work: cost per task, per merged pull request, and per delivery sprint, with forecasts leadership can plan against under an active cost-reduction programme.
- Right-size model selection per task tier across frontier and smaller reasoning models — routing routine work down and reserving frontier capacity for genuinely hard reasoning.

Agent Configuration & Harness Design
- Own system prompts, agent instructions, and repository-level configuration as versioned, reviewed artifacts — not ad hoc text pasted between engineers.
- Design the tool surface each agent gets: tool inventories, MCP servers, custom skills, subagent decomposition, and permission and sandboxing models.
- Build internal MCP servers and integrations connecting agents to the systems delivery teams actually use — repositories, Azure DevOps Boards and Repos, CI pipelines, documentation, and data platforms.
- Integrate with the client's existing AI estate rather than beside it: OpenAI APIs and the Codex toolchain, GitHub Copilot, Microsoft Foundry, and agent runtimes on Amazon Bedrock / AWS AgentCore.
- Maintain a golden reference configuration set with a clear versioning, rollout, and rollback process across accounts.

Evaluation, Benchmarking & Observability
- Stand up evaluation harnesses with golden task sets drawn from real delivery work — including payment, POS, and hospitality commerce flows — so configuration changes are proven rather than assumed.
- Run controlled comparisons across models, tools, and prompt strategies, accounting for run-to-run variance before declaring a winner.
- Instrument agent runs end to end: traces, token and latency telemetry, tool-call success rates, and cost attribution by team, account, and workflow.
- Maintain a failure taxonomy — loops, hallucinated APIs, tool misuse, premature completion — and drive each recurring class to a systemic fix.
- Own the agentic metrics programme end to end: establish pre-agent baselines, publish dashboards, and defend the numbers to delivery leadership and the client.

Delivery Workflow Integration
- Embed agents into the SDLC where they earn their keep: ticket intake and refinement, scaffolding, test generation, code-review augmentation, legacy migration and refactor work, and documentation.
- Apply agents to the modernization workload specifically — core conversions, platform consolidation, and wrapping or retiring legacy COBOL / DB2 / CICS components behind modern APIs.
- Define the human-in-the-loop gates: what an agent may merge unattended, what requires review, and what it must never touch.
- Codify agentic practice into repeatable delivery playbooks and standards, so results hold across engagements rather than depending on which engineer is on the team.
- Partner with delivery leads and client stakeholders to set realistic expectations and report honest results, including where agents underperform.

Security, Governance & Enablement
- Harden agentic workflows against prompt injection, untrusted tool output, secret leakage, and unsafe autonomous actions.
- Establish governance fit for a regulated payments environment: identity-bound execution, policy enforcement, audit trails, data residency, model and vendor policy, provenance of generated code, and PCI DSS scope discipline wherever cardholder data is in reach.
- Act as the internal authority on a fast-moving field: evaluate new tooling, separate signal from marketing, and brief leadership on what genuinely changes the plan.

What You Bring

Education
- Bachelor's degree in Computer Science, Software Engineering, or a related technical field, or equivalent practical experience.

Experience
- 5+ years building and shipping production software, with real depth in at least one ecosystem.
- Travel or hospitality domain experience is mandatory — restaurant, lodging, POS, booking, ticketing, or travel-payments systems. Folios, incremental authorisations, no-show and cancellation handling, tip adjustments, and multi-property settlement are the domain, not decoration.
- Hands-on production experience with OpenAI — APIs, the Codex toolchain, or agent frameworks built on OpenAI models — beyond casual use.
- Hands-on production use of agentic coding tools (Codex, Claude Code, Cursor, GitHub Copilot, or comparable).
- Demonstrated work on context engineering, agent optimisation, or LLM evaluation, with measured outcomes you can talk through.

Technical Expertise
- Strong Python and/or TypeScript; comfortable building tooling, harnesses, and integrations.
- Working knowledge of LLM mechanics: context windows, tokenisation, caching, sampling, and tool calling — and where each breaks.
- Solid CI/CD, version control, and testing fundamentals.
- Hands-on Microsoft Azure DevOps — Boards, Repos, and Pipelines — and able to integrate agentic workflows into that toolchain.

Soft Skills
- Measurement discipline: instrument first, form a hypothesis, and let the data overrule intuition.
- English at C1 level, able to explain trade-offs to engineers and executives alike.

Nice to Have
- Payments or financial-services delivery — acquiring, issuing, core banking, or merchant processing.
- Amazon Bedrock and AWS AgentCore, or Microsoft Foundry and GitHub Copilot, at enterprise scale.
- MCP server development or open-source agentic tooling contributions.
- Hospitality platform integration — PMS, kitchen display, kiosk, mobile order and pay, loyalty.
- Legacy modernization: mainframe wrap-and-extend, core conversion, platform consolidation.
- Developer experience, platform engineering, or SRE background.
- Evaluation frameworks, LLM observability platforms, or DORA-style delivery metrics.
- PCI DSS 4.0, SOC 2, or model-risk governance exposure.