{"id":1342088,"url":"https://alion.io/job/pitney-bowes-advisory-software-engineer","title":"Advisory Software Engineer","company":{"id":1764563,"name":"Pitney Bowes","domain":"pitneybowes.com","url":"https://alion.io/company/pitneybowes-com","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Noida, India","Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":13000,"max_usd":34000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":123},"experience_years_min":6,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"AWS Bedrock AgentCore","optional":false},{"name":"Copilot","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Hybrid Search","optional":false},{"name":"Java","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Python","optional":false},{"name":"Scrum","optional":false},{"name":"SLI/SLO/SLA","optional":false},{"name":"Azure","optional":true},{"name":"Function Calling","optional":true},{"name":"Kanban","optional":true},{"name":"RAG","optional":true},{"name":"Snowflake","optional":true},{"name":"Vertex AI Agent Builder","optional":true}],"status":"live","first_seen_at":"2026-09-02T00:00:00Z","employer_posted_date":"2026-09-02","last_verified_at":"2026-09-28T04:02:37Z","board_verified":true,"closed_at":null,"days_open":26,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":26},"description":"We’re hiring at Pitney Bowes, where top talent builds meaningful careers and lasting impact. We Move fast, Deliver excellence, and Win together…that’s The Pitney Bowes way. Here, how we work matters just as much as what we achieve.\nWe’re looking for people who:\nAct with urgency, accountability, and purpose\n\nDeliver high quality work with consistency and pride\n\nCollaborate effectively and elevate those around them\n\nFocus on outcomes that drive impact and growth\n\nJob Description:\nJoin Pitney Bowes as Advisory Software Engineer\nYears of Experience: 6-8 years\nRole: Fulltime(3 days/week in office)\nJob Location: Pune/Noida\nAbout the role\nThe AI CoE builds and ships agentic AI systems that sit on top of our core product APIs - a Copilot platform on Amazon Bedrock AgentCore, MCP-based tool servers, and AI advisors embedded in our shipping products. We are past the demo stage and into the part that is genuinely hard: making non-deterministic systems reliable, governed, measurable, and safe enough to put in front of customers and internal users.\nThis role owns the backlog and the delivery cadence for that work. You are the single throat to choke for what the team builds next and the reason the team can build it without friction. You will spend your day equally between defining outcomes with engineering, product, and security stakeholders - and clearing the path so the pod can actually deliver them.\nThis is a hands-on-the-details role, not a ceremony-running role. You will be expected to read an architecture diagram, argue about where the human-in-the-loop gate belongs, and write acceptance criteria for a system whose output is different every time you run it.\nWhat you will own\nProduct ownership\nOwn and groom the backlog for one or more AI pods (agent platform, AI advisor products, or AI productivity tooling). Set sprint goals that ladder to quarterly outcomes, not activity.\n\nTranslate ambiguous executive intent (\"we need an agent that helps SMBs ship smarter\") into epics, stories, and acceptance criteria engineers can start on Monday.\n\nWrite acceptance criteria for probabilistic systems: define what \"good\" means for an agent response, what the eval set is, what the pass threshold is, and what the failure mode is when it misses.\n\nOwn the definition of done for agent capabilities - including evals, guardrails, observability, cost per interaction, and rollback path, not just \"the happy path works.\"\n\nPrioritize ruthlessly across competing stakeholders: product management, engineering leadership, security, architecture, and the business units consuming the platform.\n\nMaintain the tool and capability catalog for the agent platform - which APIs are exposed as agent tools, which are approval-gated, which are read-only, and why.\n\nScrum mastery and delivery\nRun sprint planning, standup, review, and retrospective for the pod. Keep them short and keep them useful.\n\nTrack and report delivery health: velocity, cycle time, spillover, blocked-time. Bring problems forward early rather than explaining them in hindsight.\n\nRemove impediments - cross-team dependencies, environment access, security review queues, vendor bottlenecks. Escalate with a proposed resolution, not just a flag.\n\nFacilitate estimation and scope negotiation in a domain where estimates are genuinely uncertain, without letting uncertainty become an excuse.\n\nCoordinate across pods and with partner teams (platform engineering, data, security, product) so integration work is planned rather than discovered.\n\nTechnical stewardship\nPartner with the architecture lead on target-state decisions and carry those decisions into the backlog with enough fidelity that they survive contact with implementation.\n\nMaintain requirement traceability from product requirements through to delivered agent behavior, including where a requirement was deliberately descoped and why.\n\nOwn the AI governance checkpoints in the delivery flow: model approval, data handling review, human-in-the-loop placement, prompt and tool change control, and audit evidence.\n\nKeep a live view of platform economics - token spend, model selection, inference cost per use case - and treat cost regressions as defects.\n\nRun POCs as time-boxed experiments with a written decision at the end, not as open-ended projects.\n\nWhat success looks like\nFirst 90 days\nYou know the platform architecture well enough to explain it to a VP without an engineer in the room.\n\nThe backlog for your pod is groomed two sprints deep with acceptance criteria that engineers do not have to re-litigate in planning.\n\nYou have identified and closed the three largest sources of delivery friction for the pod.\n\nBy six months\nPredictable delivery: sprint goals met consistently, spillover trending down, dependencies surfaced before they block.\n\nEvery shipped agent capability has an eval set, a guardrail spec, and a cost-per-interaction number attached to it.\n\nStakeholders across product, engineering, and security come to you for status rather than assembling it themselves.\n\nWhat you will build\nAgent runtime and orchestration - multi-agent systems on Bedrock AgentCore: routing, session and memory management, tool selection, retry and fallback behavior, and human-in-the-loop approval gates for actions that cost money.\n\nMCP tool servers - clean, well-scoped tool interfaces over production APIs (address validation, rate shopping, label creation, tracking). Deciding what not to expose is as much of the job as building what you do.\n\nRetrieval and grounding - ingestion pipelines, chunking and embedding strategy, vector and hybrid search, and freshness guarantees over documentation, contracts, and operational data.\n\nEvaluation and guardrails - golden datasets, automated regression gates in CI, LLM-as-judge harnesses, input/output filtering, PII handling, and prompt-injection defenses on any tool that touches untrusted content.\n\nPlatform plumbing - auth and identity propagation across agent and tool layers, rate limiting, caching, cost and token instrumentation, tracing, and the dashboards that tell us when quality has quietly regressed.\n\nWhat you will do\nDesign and ship production backend services in Python and/or Java on AWS, with the tests, observability, and runbooks that make them supportable at 2am.\n\nTake an ambiguous capability (\"the agent should recommend a cheaper carrier when SLA allows\") and drive it to a designed, evaluated, instrumented, deployed feature.\n\nWrite and review architecture and design docs. Argue the trade-offs in writing before the code exists.\n\nBuild evals alongside features. A capability without a regression test is not done.\n\nOwn cost and latency as first-class engineering constraints - model selection, prompt size, caching, and parallelism are your levers.\n\nParticipate in code review, on-call rotation, and incident response. Write blameless postmortems.\n\nPreferred qualifications\nHands-on exposure to a managed agent platform (Amazon Bedrock / AgentCore, Azure AI Foundry, Vertex AI Agent Builder) and to MCP or a comparable tool-integration protocol.\n\nExperience defining evaluation frameworks for LLM systems - golden sets, LLM-as-judge, human review loops, regression gating.\n\nFamiliarity with enterprise data platforms (Snowflake or equivalent) and with data governance constraints on AI systems.\n\nExperience operating inside an AI governance or model risk process in a regulated or enterprise environment.\n\nBackground in logistics, shipping, supply chain, or B2B SaaS.\n\nCSPO, PSPO, CSM, PSM, or SAFe certification - useful, not a substitute for judgment.\n\nDesired Competencies\n5+ years in technical product ownership, technical program management, or engineering delivery leadership on software platforms - with at least 2 years directly accountable for a backlog.\n\nDemonstrated experience delivering AI/ML or LLM-based features to production. Prototypes and pilots count only if you can describe what broke when real users arrived.\n\nWorking fluency with modern AI application patterns: prompting, RAG, tool/function calling, agent orchestration, evaluation, and guardrails. You do not need to write the code; you need to reason about the design.\n\nStrong API literacy - you can read an OpenAPI spec, understand auth models, and reason about latency, idempotency, and error handling.\n\nProven Scrum or Kanban facilitation with distributed teams, including offshore or multi-timezone pods.\n\nExcellent written communication. This role produces a lot of writing that executives read.\n\nComfort with ambiguity and with saying \"not this sprint\" to senior stakeholders.\n\nThe Team\nPitney Bowes (NYSE: PBI) is a global shipping and mailing company that provides technology, logistics, and financial services to more than 90 percent of the Fortune 500. Small business, retail, enterprise, and government clients around the world rely on Pitney Bowes to remove the complexity of sending mail and parcels. For additional information visit Pitney Bowes at www.pitneybowes.com.\nWe will:\nProvide the will: opportunity to grow and develop your career\nOffer an inclusive environment that encourages diverse perspectives and ideas\nDeliver challenging and unique opportunities to contribute to the success of a transforming organization\nOffer comprehensive benefits globally (PB Benefits and Wellbeing Programs)\nPitney Bowes is an equal opportunity employer that values diversity and inclusiveness in the workplace.\nAll interested individuals must apply online.","description_format":"text","description_chars":9445,"description_truncated":false,"requirements":{"experience_years_min":6,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Commerce","Higher Education","Marketplaces"],"lifecycle":[{"event":"open","at":"2026-09-27T15:57:13Z"}],"liveness":{"score":65,"band":"ok","label":"Likely open","p_open":1,"p_active":0.721,"p_room":0.9,"age_days":26,"expected_fill_days":40,"reasons":["conf:1","win:mid"],"computed_at":"2026-09-28T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/pitney-bowes-advisory-software-engineer","json_url":"https://alion.io/job/pitney-bowes-advisory-software-engineer.json","meta":{"generated_at":"2026-09-28T22:28:20Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":277,"day_limit":5000,"remaining_today":4723,"minute_limit":60,"resets_at":"2026-09-29T00:00:00Z"}}}